From 8044111a1b11cd68fbd1a4a9f76754fdc3ebb500 Mon Sep 17 00:00:00 2001 From: Thomas Lemoine Date: Wed, 21 Jun 2023 00:45:40 -0400 Subject: [PATCH] commented change in authors' type from str to list --- src/dataset/create_dataset.py | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/src/dataset/create_dataset.py b/src/dataset/create_dataset.py index 6fe1e3f..ec20044 100644 --- a/src/dataset/create_dataset.py +++ b/src/dataset/create_dataset.py @@ -65,8 +65,8 @@ class ChunkedARD: 'title': str, 'url': str, 'date_published': str, - 'authors': list, # It appears to be a list, but actually it's a list-looking string. Like "['apple', 'orange', 'tomato']" is a string. -# 'summary': str # see previous comment + 'authors': list, # unsure as of yet if this is a string or a list. TODO it is subject to change +# 'summary': list # see previous comment } required_metadata_keys = ['id', 'source', 'title', 'text'] @@ -115,6 +115,7 @@ class ChunkedARD: url: str = entry['url'] date_published: str = entry['date_published'] authors: list = entry['authors'] + # summary is ignored for now, since most sources lack one. TODO: add summary. see self.metadata code as well. # Get signature if authors: